Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AlphaEvolve: Gemini-powered coding agent scaling impact across fields

deepmind.google

Post reply on HN
Print view View original

151–159 of 159 posts

Re: AlphaEvolve: Gemini-powered coding agent scaling impact across fields

#151

Post by mrdomino- »

nl wrote: post #130
mrdomino- wrote: post #119

Earlier quoted context omitted.

It ceases to become tacit as soon as it is collected. Maybe this rephrase will help: the proposed solution is to render all knowledge explicit.

> It ceases to become tacit as soon as it is collected. I'm not sure. It it is collected via preferences then it isn't necessarily something that can be communicated (except in the LLM's latent space). That still feels tacit to me. To simplify that argument, the relationship between King and Queen in the Word2Vec latent space can be easily explicitly labelled. But the relationship between Napoleon and Tsar Alexander…

It's a good question, yeah, and a lot of these boundaries get fuzzy when they're looked at closely enough.

It's certainly the case that LLMs already are able to represent and make use of some kinds of apparently still tacit knowledge, and that the scope of that is apparently expanding. I don't question that. I question two things: whether it is always desirable for that scope to expand, and whether it is possible for that scope to ever fully cover what it seeks to cover.

Re: AlphaEvolve: Gemini-powered coding agent scaling impact across fields

#152

Post by nerdsniper »

byzantinegene wrote: post #132
01100011 wrote: post #124

Earlier quoted context omitted.

The past few years has seen a great rise in casuals reminding us of AIs limitations only to be proven wrong in 6 months. I don't think we're close to AGI, but in 2 years I've gone from AI doubter to AI convert. It's not perfect, but I don't need it to be. The real question to me is if the system can pay for itself. Economics are racing against efficiency gains and it's anyone's guess which wins.

what are those limitations we're talking about? seems most of those the original limitations that people complained about were resolved through workarounds like tools and skills which are more software-engineering than llm advancement.

The biggest limitation I see right now is weak “theory of mind”. It’s why even though AI can generate very decent exposition, it sucks at generating narrative. This also reflects in weak performance at humor, art, and even shows up in exposition (resulting in reactions akin to “cool story bro, but why should I care?”)

It’s why people can identify AI writing even if it doesn’t contain any LLMisms. AI’s generate text that almost looks like a human wrote it, but that no human would ever actually write - when we try to imagine what kind of person would have wrote this, we draw a blank - no one we’ve ever met would have written it like that - not even any archetype we’ve ever built an internal model for.

Re: AlphaEvolve: Gemini-powered coding agent scaling impact across fields

#153

Post by jatora »

j2kun wrote: post #142
jatora wrote: post #141

Earlier quoted context omitted.

Lie? Gemini CLI is unuseable. The IF of gemini models is atrocious. Honestly, how often does your gemini CLI go insane in thought loops and you have to stop it?

I use Jetski.

what does that have to do with gemini coding?

Re: AlphaEvolve: Gemini-powered coding agent scaling impact across fields

#154

Post by berlianta »

kaueg wrote: post #93

Welcome to HN @berlianta; TIL green username === new user in HN; Stories posted by new users are called noobstories [1]; [1]: https://news.ycombinator.com/noobstories

No need for a welcome message, just stick to the topic. Thank you

Re: AlphaEvolve: Gemini-powered coding agent scaling impact across fields

#155

Post by danpalmer »

fractorial wrote: post #137
danpalmer wrote: post #131

Earlier quoted context omitted.

Happy to chat internally if you want, feel free to reach out. I see a lot of people swearing by one model, but without trying others. I see a lot of opinions based on a snapshot of tooling from ~January, when for example Claude Code was exceptional, but that don't appear to have been updated. In blind tests the models appear to be much closer than some folks would have you believe.

I’ll admit it swings back and forth on a six month cycle or so; however, cost-to-output matters. Also, for niche use-cases there are clear winners.

Google models are well known for being quite terse and efficient on cost – reasonably low pricing for what they are and reasonably low token use for what they achieve.

But as I said do reach out if you are actually a googler, as my points are really about the internal tech which I am pretty positive about.

Re: AlphaEvolve: Gemini-powered coding agent scaling impact across fields

#156

Post by DoctorOetker »

poisonfountain wrote: post #110
momojo wrote: post #92

Earlier quoted context omitted.

> Models are starting to get good at ambiguity That's fair, and something I've observed too. I wish I had written "the rest of us shouldn't freak out and quit software today". But here's another data point: At the biotech I work for, writing good code has never been the bottleneck. I actually told my boss that a paid Claude vs free subscription wouldn't be that much value because even if it took every piece of code o…

Ok, but you job is clearly not a good sample for a "job most mortals work on".

Everybody likes to think their job or specialization is the bottleneck.

I think the domain knowledge and scientific knowledge is more often the bottleneck than people like to admit.

Sure it doesn't take a lot of knowledge to repeat or automate what the previous generations did, but such decisions were very far from the optimum considering the actual scientific frontier.

Re: AlphaEvolve: Gemini-powered coding agent scaling impact across fields

#157

Post by stogot »

Groxx wrote: post #52
dekhn wrote: post #30

Earlier quoted context omitted.

If you mean specifically the Gemini VS Code Extension: it's terrible compared to Claude Code or Codex. I don't know how they can get away with it. Just constant timeouts, weird failure modes, have to start a new chat to switch modes... but I don't think any of that is specific to gemini the model- it seems to be the extension. As for actual solutions to problems ignoring the VS Code extension aspect, I find all three…

The overall quality of LLM coding tools is shockingly bad. I haven't found a single one without major issues, and many have the same problems reappear every few months, sometimes bad enough to almost break the entire thing (e.g. 100% failure rate in editing files, broken for weeks, with the same cause each time, multiple times in a year). I'd say I'm surprised by it, but uh

Which tools were these So I can avoid

Re: AlphaEvolve: Gemini-powered coding agent scaling impact across fields

#158

Post by antonvs »

HardCodedBias wrote: post #148
antonvs wrote: post #139

Earlier quoted context omitted.

> But Google being the only company in the world without access (except for GDM+labs) to a competent coding agent will take a toll. I doubt it. I use Gemini CLI daily because Gemini is what work pays for, and I have a personal Claude account. The difference is not that great, especially if you're not doing full vibe-coding. It's unlikely to have the kind of effect you're describing.

I agree with the fact that your company has quota and allocates some to you. Gemini will conduct seconds to minutes of work before requesting aid. And it will commonly fall over. Claude/Codex will commonly do minutes to hours of work. The difference is one to two orders of magnitude. It is immense.

I look forward to seeing that play out in the market, if true. But from what I've seen, it really isn't.

If you're talking about the ability to churn out low-stakes systems like websites, or variations on existing widely available systems, then perhaps. But once you get to more complex systems, especially large already existing systems, all LLMs today need significant ongoing assistance to prevent them from going off the rails and down rabbit holes. At that point, the advantage you're claiming tends to evaporate.

Re: AlphaEvolve: Gemini-powered coding agent scaling impact across fields

#159

Post by gekoxyz »

DeathArrow wrote: post #121
danpalmer wrote: post #108

Earlier quoted context omitted.

Yes. The models are good, the models are fast , and the internal tooling has caught up at this point too. There's a lot of UI/UX/tooling stuff that's still being worked through, integrations with VCS, and solving deeper problems that I probably can't talk about, but I'd say the frustrations of most are about the rate of change much more than the actual abilities. One thing that's interesting is a bunch of internal th…

>One thing that's interesting is a bunch of internal thought leaders who swear by the Flash models over the Pro models. I've seen people outside Google favoring flash Gemini models over the Pro. There are also some benchmarks where flash models have higher scores, so yes, apparently speed does matter.

as @goldenarm said just below here, I can't use Gemini Flash for how much it hallucinates. Gemini pro is quite speedy so I am good with using that. On another note, I really like deepseekv4 flash
Post reply on HN